diff mbox series

[2/2,SRU,OEM-6.1,EOM-6.0] UBUNTU: SAUCE: ata: libata: Defer rescan on suspended device

Message ID 20230505090941.384230-3-acelan.kao@canonical.com
State New
Headers show
Series A deadlock issue in scsi rescan task while resuming from S3 | expand

Commit Message

AceLan Kao May 5, 2023, 9:09 a.m. UTC 
From: Kai-Heng Feng <kai.heng.feng@canonical.com>

BugLink: https://launchpad.net/bugs/2018566

During system resume, if an EH is schduled after ATA host is resumed
(i.e. ATA_PFLAG_PM_PENDING cleared), but before the disk device is
fully resumed, the device_lock hold by scsi_rescan_device() is never
released so the dpm_resume() of the disk is blocked forerver.

That's because scsi_attach_vpd() is expecting the disk device is in
operational state, as it doesn't work on suspended device.

To avoid such deadlock, defer rescan if the disk is still suspended so
the resume process of the disk device can proceed. At the end of the
resume process, use the complete() callback to schedule the rescan task.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
(cherry picked from commit https://patchwork.ozlabs.org/project/linux-ide/patch/20230502150435.423770-2-kai.heng.feng@canonical.com/)
Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao@canonical.com>
---
 drivers/ata/libata-core.c | 11 +++++++++++
 drivers/ata/libata-eh.c   | 11 +++++++++--
 include/linux/libata.h    |  1 +
 3 files changed, 21 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index a5ea144722fa..fec17fd1f49f 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5058,6 +5058,16 @@  static int ata_port_pm_poweroff(struct device *dev)
 	return 0;
 }
 
+static void ata_port_pm_complete(struct device *dev)
+{
+	struct ata_port *ap = to_ata_port(dev);
+
+	if (ap->pflags & ATA_PFLAG_DEFER_RESCAN)
+		schedule_work(&(ap->scsi_rescan_task));
+
+	ap->pflags &= ~ATA_PFLAG_DEFER_RESCAN;
+}
+
 static const unsigned int ata_port_resume_ehi = ATA_EHI_NO_AUTOPSY
 						| ATA_EHI_QUIET;
 
@@ -5123,6 +5133,7 @@  static const struct dev_pm_ops ata_port_pm_ops = {
 	.thaw = ata_port_pm_resume,
 	.poweroff = ata_port_pm_poweroff,
 	.restore = ata_port_pm_resume,
+	.complete = ata_port_pm_complete,
 
 	.runtime_suspend = ata_port_runtime_suspend,
 	.runtime_resume = ata_port_runtime_resume,
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 08e11bc312c2..83aeeed03196 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -15,6 +15,7 @@ 
 #include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/suspend.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_eh.h>
@@ -2972,8 +2973,14 @@  static int ata_eh_revalidate_and_attach(struct ata_link *link,
 			 */
 			ehc->i.flags |= ATA_EHI_SETMODE;
 
-			/* schedule the scsi_rescan_device() here */
-			schedule_work(&(ap->scsi_rescan_task));
+			/* Schedule the scsi_rescan_device() here.
+			 * Defer the rescan if it's in process of
+			 * suspending or resuming.
+			 */
+			if (pm_suspend_target_state != PM_SUSPEND_ON)
+				ap->pflags |= ATA_PFLAG_DEFER_RESCAN;
+			else
+				schedule_work(&(ap->scsi_rescan_task));
 		} else if (dev->class == ATA_DEV_UNKNOWN &&
 			   ehc->tries[dev->devno] &&
 			   ata_class_enabled(ehc->classes[dev->devno])) {
diff --git a/include/linux/libata.h b/include/linux/libata.h
index fe990176e6ee..a1f2e1a9b546 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -189,6 +189,7 @@  enum {
 	ATA_PFLAG_UNLOADING	= (1 << 9), /* driver is being unloaded */
 	ATA_PFLAG_UNLOADED	= (1 << 10), /* driver is unloaded */
 
+	ATA_PFLAG_DEFER_RESCAN	= (1 << 16), /* peform deferred rescan on system resume */
 	ATA_PFLAG_SUSPENDED	= (1 << 17), /* port is suspended (power) */
 	ATA_PFLAG_PM_PENDING	= (1 << 18), /* PM operation pending */
 	ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */